1 citations · 1 across the 8 of their papers we have counts for
8 papers
A Unified Framework for Quantized and Continuous Strong Lottery Tickets
Aakash Kumar, Emanuele Natale
The Strong Lottery Ticket Hypothesis (SLTH) asserts that sufficiently overparameterized, randomly initialized neural networks contain sparse subnetworks that, even without any trai…
Compositional Generalization in Autoregressive Models via Logit Composition
Aakash Kumar, Maria Sofia Bucarelli, Emanuele Natale
Composing autoregressive models remains a core challenge in understanding how large language models can combine behaviors or skills learned across tasks. We introduce a new and pri…
Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks
Aakash Kumar, Anatoly Khina, Frederik Mallmann-Trenn +1
Classical Hopfield networks are limited to static patterns due to symmetric weights, whereas asymmetric networks can encode temporal sequences via limit-cycle attractors. Achieving…
Quantization vs Pruning: Insights from the Strong Lottery Ticket Hypothesis
Aakash Kumar, Emanuele Natale
Quantization is an essential technique for making neural networks more efficient, yet our theoretical understanding of it remains limited. Previous works demonstrated that extremel…
Sparse Points to Dense Clouds: Enhancing 3D Detection with Limited LiDAR Data
Aakash Kumar, Chen Chen, Ajmal Mian +2
3D detection is a critical task that enables machines to identify and locate objects in three-dimensional space. It has a broad range of applications in several fields, including a…
Advanced Efficient Strategy for Detection of Dark Objects Based on Spiking Network with Multi-Box Detection
Munawar Ali, Baoqun Yin, Hazrat Bilal +3
Several deep learning algorithms have shown amazing performance for existing object detection tasks, but recognizing darker objects is the largest challenge. Moreover, those techni…
Applying adversarial networks to increase the data efficiency and reliability of Self-Driving Cars
Aakash Kumar
Convolutional Neural Networks (CNNs) are vulnerable to misclassifying images when small perturbations are present. With the increasing prevalence of CNNs in self-driving cars, it i…
PC-DAN: Point Cloud based Deep Affinity Network for 3D Multi-Object Tracking (Accepted as an extended abstract in JRDB-ACT Workshop at CVPR21)
Aakash Kumar, Jyoti Kini, Mubarak Shah +1
In recent times, the scope of LIDAR (Light Detection and Ranging) sensor-based technology has spread across numerous fields. It is popularly used to map terrain and navigation info…